Research map / 3D vision / 3D generation
EgoCogNav: Cognition-aware Human Egocentric Navigation
Zhiwen Qiu, Ziang Liu, Wenqian Niu, Tapomayukh Bhattacharjee, Saleh Kalantari
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add uncertainty prediction head (ablation) | base module · CEN test (all scenarios) | FDE: .2443 -> .2217 | Improved |
| add uncertainty prediction head (ablation) | base module · CEN test (all scenarios) | Head L1: .0785 -> .0721 | Improved |
| add uncertainty-conditioned decoding on top of U prediction (ablation) | EgoCogNav · CEN test (all scenarios) | FDE: .2217 -> .2188 | No clear effect |
| add memory on top of U prediction (ablation) | EgoCogNav · CEN test (all scenarios) | FDE: .2217 -> .2193 | No clear effect |
| combine UCD and memory (ablation) | EgoCogNav · CEN test (all scenarios) | FDE: .2188 -> .2074 | Improved |
| combine UCD and memory (ablation) | EgoCogNav · CEN test (high-U scenarios) | ADE: .1212 -> .1155 | Improved |
| add video features to motion and goal (ablation) | EgoCogNav inputs · CEN modality ablation | FDE: .313 -> .213 | Improved |
| add video features to motion and goal (ablation) | EgoCogNav inputs · CEN modality ablation | Spearman rho: .314 -> .778 | Improved |
| add goal to motion (ablation) | EgoCogNav inputs · CEN modality ablation | FDE: .314 -> .313 | No clear effect |
| add head history to video (ablation) | EgoCogNav inputs · CEN modality ablation | Head L1: .0713 -> .0708 | Improved |
| add head history to video (ablation) | EgoCogNav inputs · CEN modality ablation | FDE: .213 -> .217 | Hurt |
| add gaze to motion, video and head (ablation) | EgoCogNav inputs · CEN modality ablation | FDE: .217 -> .207 | Improved |
Closest papers by meaning
- EgoTraj: Real-World Egocentric Human Trajectory (ECCV 2026 · similarity 0.90)
- Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span (NeurIPS 2025 · similarity 0.88)
- EgoGen: An Egocentric Synthetic Data Generator (CVPR 2024 · similarity 0.87)
- RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments (CVPR 2025 · similarity 0.86)
- Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding (NeurIPS 2025 · similarity 0.85)
- Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
